Mining Hierarchical Temporal Patterns in Multivariate Time Series

Abstract. The Unification-based Temporal Grammar is a temporal extension of static unification-based grammars. It defines a hierarchical temporal rule language to express complex patterns present in multivariate time series. The Temporal Data Mining Method is the accompanying framework to discover temporal knowledge based on this rule language. A semiotic hierarchy of temporal patterns, which are not a priori given, is build in a bottom up manner from static logical descriptions of multivariate time instants. We demonstrate the methods using music data, extracting typical parts of songs.

• Type: Conference
• Year: 2004
• Where: KI
• Authors: Fabian Mörchen, Alfred Ultsch
• Keywords: Hierarchical Temporal Rule, KI 2004, Temporal Extension, Unification-based Temporal Grammar